{"id":"https://openalex.org/W2397098974","doi":"https://doi.org/10.21437/interspeech.2014-294","title":"Lipreading approach for isolated digits recognition under whisper and neutral speech","display_name":"Lipreading approach for isolated digits recognition under whisper and neutral speech","publication_year":2014,"publication_date":"2014-09-14","ids":{"openalex":"https://openalex.org/W2397098974","doi":"https://doi.org/10.21437/interspeech.2014-294","mag":"2397098974"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2014-294","doi":"https://doi.org/10.21437/interspeech.2014-294","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2014-294","pdf_url":null,"source":{"id":"https://openalex.org/S4393918409","display_name":"Interspeech (USB)","issn_l":"2308-457X","issn":["2308-457X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2014","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101452102","display_name":"Fei Tao","orcid":"https://orcid.org/0000-0003-4834-8949","observed_orcids":["https://orcid.org/0000-0003-4834-8949"]},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fei Tao","raw_affiliation_strings":["University of Texas at Dallas"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Dallas","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040793194","display_name":"Carlos Busso","orcid":"https://orcid.org/0000-0002-4075-4072","observed_orcids":["https://orcid.org/0000-0002-4075-4072"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Carlos Busso","raw_affiliation_strings":["Electrical Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electrical Engineering","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.5123,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":{"value":0.91953831,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1154","last_page":"1158"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.8407999873161316,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.8407999873161316,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.14720000326633453,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10403","display_name":"Phonetics and Phonology Research","score":0.0017999999690800905,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/lip-reading","display_name":"lip reading","score":0.9909999966621399},{"id":"https://openalex.org/keywords/isolated-digit-recognition","display_name":"isolated digit recognition","score":0.8920000195503235},{"id":"https://openalex.org/keywords/audio-visual-speech-recognition","display_name":"audio-visual speech recognition","score":0.8119999766349792},{"id":"https://openalex.org/keywords/hidden-markov-models","display_name":"hidden Markov models","score":0.859000027179718},{"id":"https://openalex.org/keywords/speaker-adaptation","display_name":"speaker adaptation","score":0.6959999799728394}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8655569553375244},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8330796957015991},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6897947788238525},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.5394819974899292},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44284239411354065},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.42792195081710815},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.42761752009391785},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.41998594999313354},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33599692583084106},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.33507266640663147},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2014-294","doi":"https://doi.org/10.21437/interspeech.2014-294","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2014-294","pdf_url":null,"source":{"id":"https://openalex.org/S4393918409","display_name":"Interspeech (USB)","issn_l":"2308-457X","issn":["2308-457X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2014","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"id":"https://metadata.un.org/sdg/16","score":0.6499999761581421,"display_name":"Peace, justice, and strong institutions"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W32775615","https://openalex.org/W1536024295","https://openalex.org/W1576996184","https://openalex.org/W1820427070","https://openalex.org/W1991893800","https://openalex.org/W2011646888","https://openalex.org/W2020596545","https://openalex.org/W2022047569","https://openalex.org/W2041470347","https://openalex.org/W2046599127","https://openalex.org/W2076017598","https://openalex.org/W2096391593","https://openalex.org/W2098923380","https://openalex.org/W2108492645","https://openalex.org/W2113786253","https://openalex.org/W2121027212","https://openalex.org/W2122817389","https://openalex.org/W2124397839","https://openalex.org/W2151046079","https://openalex.org/W2157827878","https://openalex.org/W2164598857","https://openalex.org/W2165949425","https://openalex.org/W2168996682","https://openalex.org/W2171246813","https://openalex.org/W2341824394","https://openalex.org/W3099202502"],"related_works":["https://openalex.org/W1536024295","https://openalex.org/W1932556451","https://openalex.org/W2041470347","https://openalex.org/W2121015323","https://openalex.org/W1981970480","https://openalex.org/W2083892355","https://openalex.org/W2133906911","https://openalex.org/W4242230814","https://openalex.org/W4302789782","https://openalex.org/W2126463201"],"abstract_inverted_index":{"Whisper":[0],"is":[1,38],"a":[2],"speech":[3,23,64],"production":[4],"mode":[5],"normally":[6],"used":[7],"to":[8,34,57,113],"protect":[9],"confidential":[10],"information.":[11],"Given":[12],"the":[13,16,19,36,39,46,52,73,77,81,87,98,115,122,125,131,137],"differences":[14],"in":[15,93,130],"acoustic":[17],"domain,":[18],"performance":[20,37,99,123],"of":[21,41,48,80,124,133,139],"automatic":[22],"recognition":[24],"(ASR)":[25],"systems":[26],"decreases":[27,100],"with":[28],"whisper":[29,63,83,134,146],"speech.":[30],"An":[31],"appealing":[32],"approach":[33],"improve":[35],"use":[40,47],"lipreading.":[42],"This":[43],"study":[44],"explores":[45],"visual":[49,141],"features":[50,75],"characterizing":[51],"lips\u2019":[53],"geometry":[54],"and":[55,62],"appearance":[56],"recognize":[58],"digits":[59],"under":[60],"normal":[61],"conditions":[65,96],"using":[66,140],"hidden":[67],"Markov":[68],"models":[69,106],"(HMMs).":[70],"We":[71,108],"evaluate":[72,103],"proposed":[74,88],"on":[76],"digit":[78],"part":[79],"audiovisual":[82],"(AVW)":[84],"corpus.":[85],"While":[86],"system":[89],"achieves":[90],"high":[91],"accuracy":[92],"speaker":[94,104],"dependent":[95],"(80.8%),":[97],"when":[101],"we":[102],"independent":[105],"(52.9%).":[107],"propose":[109],"supervised":[110],"adaptation":[111],"schemes":[112],"reduce":[114],"mismatch":[116],"between":[117],"speakers.":[118],"Across":[119],"all":[120],"conditions,":[121],"classifiers":[126],"remain":[127],"competitive":[128],"even":[129],"presence":[132],"speech,":[135,147],"highlighting":[136],"benefits":[138],"features.":[142],"Index":[143],"Terms:":[144],"Lipreading,":[145],"multimodal":[148],"corpus":[149]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":2}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2016-06-24T00:00:00"}